kali20gakki/msAgent / skills/host-cpu/msagent-perf-cpu-perf-triage
msagent-perf-cpu-perf-triage
Verified昇腾 Host 侧性能异常归因编排:训练/推理出现症状(变慢、抖动、利用率低)且原因 不明时,按「配置复核 → 归因量化」编排 config-audit 完成配置判型,并输出按 代价×收益排序的 Action。触发:训练变慢、step 抖动、性能下降、利用率低、查根因、 瓶颈在哪。 不用于:只要配置检查(→ perf-cpu-config-audit)、只要绑核方案 (→ perf-cpu-bind-tune)——窄诉求直接用对应技能更快;本技能用于症状不明、 需多源归因的场景。
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 6.7 KB |
| references/degradation.md | markdown | 2.2 KB |
| references/quant-rules.md | markdown | 3.7 KB |
| references/triage-playbook.md | markdown | 4.0 KB |
| resources/action-templates.json | config | 3.8 KB |
| resources/triage-report.template.html | other | 7.9 KB |
| scripts/action_build.py | script | 9.9 KB |
| scripts/audit_or_reuse.py | script | 8.5 KB |
| scripts/quantify.py | script | 8.1 KB |
| scripts/report.py | script | 9.6 KB |
| scripts/workspace.py | script | 4.4 KB |
scripts/workspace.py
View on GitHub# -------------------------------------------------------------------------
# This file is part of the MindStudio project.
# Copyright (c) 2026 Huawei Technologies Co.,Ltd.
#
# MindStudio is licensed under Mulan PSL v2.
# You can use this software according to the terms and conditions of the Mulan PSL v2.
# You may obtain a copy of Mulan PSL v2 at:
#
# http://license.coscl.org.cn/MulanPSL2
#
# THIS SOFTWARE IS PROVIDED ON AN "AS IS" BASIS, WITHOUT WARRANTIES OF ANY KIND,
# EITHER EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO NON-INFRINGEMENT,
# MERCHANTABILITY OR FIT FOR A PARTICULAR PURPOSE.
# See the Mulan PSL v2 for more details.
# -------------------------------------------------------------------------
"""perf-triage 工作空间与产物目录解析(与 3 个基础 Skill 同构 + 编排层扩展)。
约定:
会话根 = <workspace>/workspaces/<host>/<timestamp>/,与基础 Skill 落盘口径一致;
阶段子目录 = 00-config / 01-trace / 02-perf / actions(目录序 = 阶段序);
汇总页 index.html 与 manifest.json 固定在会话根。
优先级:显式 root 参数 > HOSTCPU_WORKSPACE > 当前工作目录(cwd)。
"""
import json
import os
import re
import socket
import tempfile
import time
PHASES = ("00-config", "01-trace", "02-perf", "actions")
RESIDUAL_CONVERGED_MAX = 30.0 # 残余占比上限,quantify/report 共用同一口径
def safe_name(value):
"""外部输入进路径前清洗:仅保留字母数字/点/横线/下划线,截断 64。"""
cleaned = re.sub(r"[^\w.-]+", "_", str(value or "")).strip("._")
return (cleaned or "unknown")[:64]
def workspace_root(root=None):
if root:
return os.path.abspath(os.path.expanduser(root))
env = os.environ.get("HOSTCPU_WORKSPACE")
if env:
return os.path.abspath(os.path.expanduser(env))
return os.path.abspath(os.getcwd())
def new_session(host=None, timestamp=None, root=None, create=True):
"""建立会话目录,返回会话描述 dict。
create=False 时只计算路径不落盘(调试/预演用)。
"""
host = safe_name(host or socket.gethostname())
ts = safe_name(timestamp or time.strftime("%Y%m%d-%H%M%S", time.localtime()))
base = os.path.join(workspace_root(root), "workspaces", host, ts)
if create:
for name in PHASES:
os.makedirs(os.path.join(base, name), exist_ok=True)
return {"run_id": "%s_%s" % (host, ts), "host": host,
"timestamp": ts, "root": base}
def phase_dir(session_root, phase, create=True):
path = os.path.join(session_root, phase)
if create:
os.makedirs(path, exist_ok=True)
return path
def load_json(path, default=None):
try:
with open(path, "r", encoding="utf-8") as fh:
return json.load(fh)
except (OSError, ValueError):
return default
def write_json(path, data):
"""原子写 JSON:先写同目录临时文件再 os.replace,避免中断留下半截文件。"""
parent = os.path.dirname(path)
if parent:
os.makedirs(parent, exist_ok=True)
fd, tmp = tempfile.mkstemp(prefix=".tmp-", suffix=".json", dir=parent or None)
try:
with os.fdopen(fd, "w", encoding="utf-8") as fh:
json.dump(data, fh, ensure_ascii=False, indent=2)
fh.flush()
os.fsync(fh.fileno())
os.replace(tmp, path)
except BaseException:
if os.path.exists(tmp):
os.remove(tmp)
raise
return path
def manifest_upsert(session_root, section, data):
"""更新 manifest.json 的某个阶段段(保持其余段不变)。
manifest 是各阶段共享的汇总文件,本函数按阶段串行调用;写回走原子替换。
文件存在但解析失败时先备份为 .corrupt-<ts> 再重建,避免静默清空其它阶段数据。
"""
path = os.path.join(session_root, "manifest.json")
manifest = {}
if os.path.isfile(path):
loaded = load_json(path)
if isinstance(loaded, dict):
manifest = loaded
else:
os.replace(path, "%s.corrupt-%s" % (path, time.strftime("%Y%m%d-%H%M%S")))
manifest.setdefault("run_id", os.path.basename(os.path.normpath(session_root)))
manifest.setdefault("phases", {})
manifest["phases"][section] = data
manifest["updated_at"] = time.strftime("%Y-%m-%d %H:%M:%S", time.localtime())
write_json(path, manifest)
return path
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |